Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74025
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IInterface
    -0.79
    migrationBuilder
    -0.69
    
    -0.66
    webElementXpaths
    -0.66
     الرياضيه
    -0.65
     Huk
    -0.63
     الحره
    -0.61
    abetes
    -0.60
    StructEnd
    -0.60
    󠁴
    -0.60
    POSITIVE LOGITS
     فريبيس
    0.51
    HtmlAttribute
    0.50
     ModelExpression
    0.43
    ecore
    0.42
     démoc
    0.42
    ASH
    0.41
    ADH
    0.40
     chré
    0.40
    oa̍t
    0.40
    WithIdentifier
    0.40
    Activations Density 0.000%

    No Known Activations